Close-range hyperspectral image analysis for the early detection of stress responses in individual plants in a high-throughput phenotyping platform

Abstract The potential of close-range hyperspectral imaging (HSI) as a tool for detecting early drought stress responses in plants grown in a high-throughput plant phenotyping platform (HTPPP) was explored. Reflectance spectra from leaves in close-range imaging are highly influenced by plant geometry and its specific alignment towards the imaging system. This induces high uninformative variability in the recorded signals, whereas the spectral signature informing on plant biological traits remains undisclosed. A linear reflectance model that describes the effect of the distance and orientation of each pixel of a plant with respect to the imaging system was applied. By solving this model for the linear coefficients, the spectra were corrected for the uninformative illumination effects. This approach, however, was constrained by the requirement of a reference spectrum, which was difficult to obtain. As an alternative, the standard normal variate (SNV) normalisation method was applied to reduce this uninformative variability. Once the envisioned illumination effects were eliminated, the remaining differences in plant spectra were assumed to be related to changes in plant traits. To distinguish the stress-related phenomena from regular growth dynamics, a spectral analysis procedure was developed based on clustering, a supervised band selection, and a direct calculation of a spectral similarity measure against a reference. To test the significance of the discrimination between healthy and stressed plants, a statistical test was conducted using a one-way analysis of variance (ANOVA) technique. The proposed analysis techniques was validated with HSI data of maize plants (Zea mays L.) acquired in a HTPPP for early detection of drought stress in maize plant. Results showed that the pre-processing of reflectance spectra with the SNV effectively reduces the variability due to the expected illumination effects. The proposed spectral analysis method on the normalized spectra successfully detected drought stress from the third day of drought induction, confirming the potential of HSI for drought stress detection studies and further supporting its adoption in HTPPP.

[1]  L. Plümer,et al.  Original paper: Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectance , 2010 .

[2]  J. Boyer,et al.  Leaf shrinkage decreases porosity at low water potentials in sunflower. , 2007, Functional plant biology : FPB.

[3]  J. M. Norman,et al.  Leaf bidirectional reflectance and transmittance in corn and soybean , 1989 .

[4]  Yufeng Ge,et al.  Temporal dynamics of maize plant growth, water use, and leaf water content using automated high throughput RGB and hyperspectral imaging , 2016, Comput. Electron. Agric..

[5]  J. Boyer,et al.  Relationship of water potential to growth of leaves. , 1968, Plant physiology.

[6]  J. Peñuelas,et al.  The reflectance at the 950–970 nm region as an indicator of plant water status , 1993 .

[7]  Victoria Pastor,et al.  Plant Responses to Simultaneous Biotic and Abiotic Stress: Molecular Mechanisms , 2014, Plants.

[8]  H. Gausman,et al.  Reflectance of leaf components , 1977 .

[9]  O. Matsuda,et al.  Hyperspectral Imaging Techniques for Rapid Identification of Arabidopsis Mutants with Altered Leaf Pigment Status , 2012, Plant & cell physiology.

[10]  Philip A. Townsend,et al.  Quantifying the influences of spectral resolution on uncertainty in leaf trait estimates through a Bayesian approach to RTM inversion , 2016 .

[11]  Hervé Cochard,et al.  Leaf Shrinkage with Dehydration: Coordination with Hydraulic Vulnerability and Drought Tolerance1[C][W][OPEN] , 2013, Plant Physiology.

[12]  G. A. Blackburn,et al.  Hyperspectral remote sensing of plant pigments. , 2006, Journal of experimental botany.

[13]  Qin Zhang,et al.  A Review of Imaging Techniques for Plant Phenotyping , 2014, Sensors.

[14]  W. Verhoef,et al.  PROSPECT+SAIL models: A review of use for vegetation characterization , 2009 .

[15]  Wei Gong,et al.  Analyzing the performance of PROSPECT model inversion based on different spectral information for leaf biochemical properties retrieval , 2018 .

[16]  A. Karnieli,et al.  Combining leaf physiology, hyperspectral imaging and partial least squares-regression (PLS-R) for grapevine water status assessment , 2015 .

[17]  F. Meer.  The effectiveness of spectral similarity measures for the analysis of hyperspectral imagery , 2006 .

[18]  F. Baret,et al.  PROSPECT: A model of leaf optical properties spectra , 1990 .

[19]  Matthew F. McCabe,et al.  A hybrid training approach for leaf area index estimation via Cubist and random forests machine-learning , 2018 .

[20]  K. Kimura,et al.  Recovery responses of photosynthesis, transpiration, and stomatal conductance in kidney bean following drought stress , 2005 .

[21]  P. Curran.  Remote sensing of foliar chemistry , 1989 .

[22]  E. B. Knipling.  Physical and physiological basis for the reflectance of visible and near-infrared radiation from vegetation , 1970 .

[23]  U. Rascher,et al.  Imaging plants dynamics in heterogenic environments. , 2012, Current opinion in biotechnology.

[24]  J. Flexas,et al.  Role of mesophyll diffusion conductance in constraining potential photosynthetic productivity in the field. , 2009, Journal of experimental botany.

[25]  Ribana Roscher,et al.  DETECTION OF DISEASE SYMPTOMS ON HYPERSPECTRAL 3D PLANT MODELS , 2016 .

[26]  Frans van den Berg,et al.  Review of the most common pre-processing techniques for near-infrared spectra , 2009 .

[27]  Lutz Plümer,et al.  Unsupervised domain adaptation for early detection of drought stress in hyperspectral images , 2017 .

[28]  Anne-Katrin Mahlein,et al.  Hyperspectral imaging for small-scale analysis of symptoms caused by different sugar beet diseases , 2012, Plant Methods.

[29]  J. Flexas,et al.  Photosynthesis under drought and salt stress: regulation mechanisms from whole plant to cell. , 2009, Annals of botany.

[30]  Yunseop Kim,et al.  Hyperspectral image analysis for water stress detection of apple trees , 2011 .

[31]  D. Lawlor,et al.  Water stress inhibits plant photosynthesis by decreasing coupling factor and ATP , 1999, Nature.

[32]  Anne-Katrin Mahlein,et al.  Recent advances in sensing plant diseases for precision crop protection , 2012, European Journal of Plant Pathology.

[33]  Gustau Camps-Valls,et al.  Hyperspectral dimensionality reduction for biophysical variable statistical retrieval , 2017 .

[34]  Malia A. Gehan,et al.  Lights, camera, action: high-throughput plant phenotyping is ready for a close-up. , 2015, Current opinion in plant biology.

[35]  J. Peñuelas,et al.  Estimation of plant water concentration by the reflectance Water Index WI (R900/R970) , 1997 .

[36]  G. Carter,et al.  Leaf optical properties in higher plants: linking spectral characteristics to stress and chlorophyll concentration. , 2001, American journal of botany.

[37]  Josep Peñuelas,et al.  Cell wall elasticity and Water Index (R970 nm/R900 nm) in wheat under different nitrogen availabilities , 1996 .

[38]  Tom Fearn.  The Effect of Spectral Pre-Treatments on Interpretation , 2009 .

[39]  R. Barnes,et al.  Standard Normal Variate Transformation and De-Trending of Near-Infrared Diffuse Reflectance Spectra , 1989 .

[40]  Andrew K. Skidmore,et al.  Retrieval of forest leaf functional traits from HySpex imagery using radiative transfer models and continuous wavelet analysis , 2016 .

[41]  Paul Scheunders,et al.  Close range hyperspectral imaging of plants: A review , 2017 .

[42]  S. Jacquemoud,et al.  Leaf BRDF measurements and model for specular and diffuse components differentiation , 2005 .

[43]  P. Geladi,et al.  Linearization and Scatter-Correction for Near-Infrared Reflectance Spectra of Meat , 1985 .

[44]  J. Féret,et al.  A physically-based model for retrieving foliar biochemistry and leaf orientation using close-range imaging spectroscopy , 2016 .

[45]  D. Roberts,et al.  Deriving Water Content of Chaparral Vegetation from AVIRIS Data , 2000 .

[46]  D. Sims,et al.  Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages , 2002 .

[47]  J. Gago,et al.  Leaf responses to drought stress in Mediterranean accessions of Solanum lycopersicum: anatomical adaptations in relation to gas exchange parameters. , 2013, Plant, cell & environment.

[48]  M. L. Osório,et al.  Influence of transient shade periods on the effects of drought on photosynthesis, carbohydrate accumulation and lipid peroxidation in sunflower leaves , 2006 .

[49]  Christian Bauckhage,et al.  Metro Maps of Plant Disease Dynamics—Automated Mining of Differences Using Hyperspectral Images , 2015, PloS one.

[50]  J. Peguero-Pina,et al.  Relationship between ultrasonic properties and structural changes in the mesophyll during leaf dehydration. , 2011, Journal of experimental botany.

[51]  Lutz Plümer,et al.  Calibration of hyperspectral close-range pushbroom cameras for plant phenotyping , 2015 .

[52]  L. Plümer,et al.  Detection of early plant stress responses in hyperspectral images , 2014 .

[53]  K. Kersting,et al.  Early drought stress detection in cereals: simplex volume maximisation for hyperspectral image analysis. , 2012, Functional plant biology : FPB.

[54]  David J. Beerling,et al.  Maximum leaf conductance driven by CO2 effects on stomatal size and density over geologic time , 2009, Proceedings of the National Academy of Sciences.

[55]  B. Demmig‐Adams,et al.  The role of xanthophyll cycle carotenoids in the protection of photosynthesis , 1996 .

[56]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[57]  Andrew M Mutka,et al.  Image-based phenotyping of plant disease symptoms , 2015, Front. Plant Sci..

[58]  G. F. Hughes,et al.  On the mean accuracy of statistical pattern recognizers , 1968, IEEE Trans. Inf. Theory.

[59]  Brian Everitt,et al.  Cluster analysis , 1974 .

[60]  Gilles Rabatel,et al.  Potential of field hyperspectral imaging as a non destructive method to assess leaf nitrogen content in Wheat , 2011 .